{
 "id": "DATA-MASK/FineWeb-Mask",
 "owner": "DATA-MASK",
 "name": "FineWeb-Mask",
 "downloads": 1291,
 "likes": 6,
 "last_modified": "2026-01-19T07:37:14.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{fan2025jointselectionlargescalepretraining,\n      title={Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning}, \n      author={Ziqing Fan and Yuqiao Xian and Yan Sun and Li Shen},\n      year={2025},\n      eprint={2512.24265},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2512.24265}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "8f5ab01fd5b74e47579961fdeae8a81c2bc5dca2",
 "stated_evidence": "https://huggingface.co/datasets/DATA-MASK/FineWeb-Mask/blob/8f5ab01fd5b74e47579961fdeae8a81c2bc5dca2/README.md",
 "file_evidence": "https://huggingface.co/datasets/DATA-MASK/FineWeb-Mask/tree/8f5ab01fd5b74e47579961fdeae8a81c2bc5dca2",
 "card_nc": false
}